From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models
Summary
This paper proposes a staged training approach for vision-language models that separates visual perception, visual reasoning, and textual reasoning into distinct stages. The method improves visual reasoning accuracy while reducing reasoning trace length, demonstrating that stronger perception reduces the need for excessive reasoning.
View Cached Full Text
Cached at: 05/25/26, 10:37 AM
Paper page - From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models
Source: https://huggingface.co/papers/2605.20177
Abstract
Staged training approaches that separately optimize visual perception, visual reasoning, and textual reasoning in vision-language models outperform unified training methods, leading to improved performance on visual reasoning tasks.
Recent advances invision-language models(VLMs) emphasize long chain-of-thought reasoning; yet, we find that their performance on visual tasks is primarily limited by a lack ofvisual perceptionas opposed to reasoning itself. In this work, we systematically study the interplay between perception and reasoning in VLM post-training by decomposing their capabilities into three separate training stages:visual perception,visual reasoning, andtextual reasoning, incorporating specialized training data. We demonstrate thatvisual perception(a) requires targeted optimization with specialized data; (b) serves as a fundamental scaffold that should be solidified throughstaged trainingbefore refiningvisual reasoning; and (c) is more effectively learned via RL than caption-based SFT. Our experiments across multiple VLMs demonstrate thatstaged trainingconsistently improves bothvisual perceptionand reasoning performance over merged training. Notably, models trained with our approach achieve 1.5% higher reasoning accuracy with 20.8% shorter reasoning traces, suggesting that superior perception reduces the need for excessive reasoning. Furthermore, we show that this capability-based staging represents a new curriculum dimension orthogonal to traditional difficulty-based curricula, and combining both yields further additive gains. Our staged-training models achieve superior performance among open-weight VLMs, establishing advanced results on severalvisual mathand perception (e.g., +5.2% onWeMathand +3.7% onRealWorldQA) tasks compared with the base counterpart.
View arXiv pageView PDFProject pageGitHub4Add to collection
Get this paper in your agent:
hf papers read 2605\.20177
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper4
#### UCSC-VLAA/VLM-CapCurriculum-InternVL3-8B-Staged Image-Text-to-Text• 8B• Updated5 days ago • 49
#### UCSC-VLAA/VLM-CapCurriculum-InternVL3.5-8B-Staged Image-Text-to-Text• 9B• Updated5 days ago • 42
#### UCSC-VLAA/VLM-CapCurriculum-Qwen3-VL-8B-Staged Image-Text-to-Text• 9B• Updated5 days ago • 49
#### UCSC-VLAA/VLM-CapCurriculum-Qwen2.5-VL-7B-Staged Image-Text-to-Text• 8B• Updated5 days ago • 48
Datasets citing this paper3
#### UCSC-VLAA/VLM-CapCurriculum-Perception-Data Viewer• Updated5 days ago • 3.36k • 88 #### UCSC-VLAA/VLM-CapCurriculum-TextReasoning-Data Viewer• Updated5 days ago • 13.2k • 65 #### UCSC-VLAA/VLM-CapCurriculum-VisualReasoning-Data
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2605.20177 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning
Introduces Perceive-to-Reason (P2R), a framework that decouples visual perception from reasoning in vision-language models using a two-stage process and a role-aware reinforcement learning strategy, achieving state-of-the-art results on fine-grained visual reasoning benchmarks.
Bad Seeing or Bad Thinking? Rewarding Perception for Vision-Language Reasoning
This paper introduces a reinforcement learning framework that improves perception-reasoning synergy in vision-language models by explicitly rewarding perceptual fidelity, using a 'blindfolded reasoning' proxy and structured verbal verification to address ambiguity in modality credit assignment.
More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models
This paper uncovers that prolonged reasoning in vision-language models can impair perceptual grounding, causing recognition failures on basic visual questions. It proposes Vision-Anchored Policy Optimization (VAPO) to steer reasoning toward visually grounded trajectories, achieving state-of-the-art performance with the VAPO-Thinker-7B model.
Seeing Before Reasoning: Decoupling Perception and Reasoning for Shortcut-Resilient Multimodal On-Policy Self-Distillation
This paper introduces ViGOS, a method for multimodal on-policy self-distillation that decouples perception and reasoning by having the student model first produce a visual description before reasoning, reducing shortcut reliance and improving image-grounding behavior.
Revisiting Complete Reasoning Traces for Post-Training
This paper finds that large language models can gain reasoning improvements from truncated reasoning trajectories rather than full ones during post-training, reducing redundancy while benefiting methods like supervised fine-tuning and reinforcement learning.